© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14951
    Prev
    Next
    INDEX
    Explanations

    assignments and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates primarily on numeric constants (e.g. literal numbers and numeric tokens) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    为例
    -0.93
     barres
    -0.93
     baile
    -0.91
     enfin
    -0.91
     molle
    -0.89
    蓠
    -0.89
     fout
    -0.88
     mets
    -0.87
     surpl
    -0.85
     semel
    -0.85
    POSITIVE LOGITS
     before
    1.06
     ważne
    0.94
    valis
    0.93
     quería
    0.93
     możliwe
    0.90
     you
    0.88
     istället
    0.88
     również
    0.88
     also
    0.86
    istad
    0.86
    Activations Density 0.003%

    No Known Activations